x86/power/64: Fix kernel text mapping corruption during image restoration

Logan Gunthorpe reports that hibernation stopped working reliably for
him after commit ab76f7b4ab23 (x86/mm: Set NX on gap between __ex_table
and rodata).

That turns out to be a consequence of a long-standing issue with the
64-bit image restoration code on x86, which is that the temporary
page tables set up by it to avoid page tables corruption when the
last bits of the image kernel's memory contents are copied into
their original page frames re-use the boot kernel's text mapping,
but that mapping may very well get corrupted just like any other
part of the page tables.  Of course, if that happens, the final
jump to the image kernel's entry point will go to nowhere.

The exact reason why commit ab76f7b4ab23 matters here is that it
sometimes causes a PMD of a large page to be split into PTEs
that are allocated dynamically and get corrupted during image
restoration as described above.

To fix that issue note that the code copying the last bits of the
image kernel's memory contents to the page frames occupied by them
previoulsy doesn't use the kernel text mapping, because it runs from
a special page covered by the identity mapping set up for that code
from scratch.  Hence, the kernel text mapping is only needed before
that code starts to run and then it will only be used just for the
final jump to the image kernel's entry point.

Accordingly, the temporary page tables set up in swsusp_arch_resume()
on x86-64 need to contain the kernel text mapping too.  That mapping
is only going to be used for the final jump to the image kernel, so
it only needs to cover the image kernel's entry point, because the
first thing the image kernel does after getting control back is to
switch over to its own original page tables.  Moreover, the virtual
address of the image kernel's entry point in that mapping has to be
the same as the one mapped by the image kernel's page tables.

With that in mind, modify the x86-64's arch_hibernation_header_save()
and arch_hibernation_header_restore() routines to pass the physical
address of the image kernel's entry point (in addition to its virtual
address) to the boot kernel (a small piece of assembly code involved
in passing the entry point's virtual address to the image kernel is
not necessary any more after that, so drop it).  Update RESTORE_MAGIC
too to reflect the image header format change.

Next, in set_up_temporary_mappings(), use the physical and virtual
addresses of the image kernel's entry point passed in the image
header to set up a minimum kernel text mapping (using memory pages
that won't be overwritten by the image kernel's memory contents) that
will map those addresses to each other as appropriate.

This makes the concern about the possible corruption of the original
boot kernel text mapping go away and if the the minimum kernel text
mapping used for the final jump marks the image kernel's entry point
memory as executable, the jump to it is guaraneed to succeed.

Fixes: ab76f7b4ab23 (x86/mm: Set NX on gap between __ex_table and rodata)
Link: http://marc.info/?l=linux-pm&m=146372852823760&w=2
Reported-by: Logan Gunthorpe <logang@deltatee.com>
Reported-and-tested-by: Borislav Petkov <bp@suse.de>
Tested-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>

1 files changed, 85 insertions, 12 deletions

diff --git a/arch/x86/power/hibernate_64.c b/arch/x86/power/hibernate_64.c
index 009947d419a6..f2b5e6a5cf95 100644
--- a/arch/x86/power/hibernate_64.c
+++ b/arch/x86/power/hibernate_64.c
@@ -19,6 +19,7 @@
 #include <asm/mtrr.h>
 #include <asm/sections.h>
 #include <asm/suspend.h>
+#include <asm/tlbflush.h>
 
 /* Defined in hibernate_asm_64.S */
 extern asmlinkage __visible int restore_image(void);
@@ -28,6 +29,7 @@ extern asmlinkage __visible int restore_image(void);
  * kernel's text (this value is passed in the image header).
  */
 unsigned long restore_jump_address __visible;
+unsigned long jump_address_phys;
 
 /*
  * Value of the cr3 register from before the hibernation (this value is passed
@@ -37,7 +39,43 @@ unsigned long restore_cr3 __visible;
 
 pgd_t *temp_level4_pgt __visible;
 
-void *relocated_restore_code __visible;
+unsigned long relocated_restore_code __visible;
+
+static int set_up_temporary_text_mapping(void)
+{
+	pmd_t *pmd;
+	pud_t *pud;
+
+	/*
+	 * The new mapping only has to cover the page containing the image
+	 * kernel's entry point (jump_address_phys), because the switch over to
+	 * it is carried out by relocated code running from a page allocated
+	 * specifically for this purpose and covered by the identity mapping, so
+	 * the temporary kernel text mapping is only needed for the final jump.
+	 * Moreover, in that mapping the virtual address of the image kernel's
+	 * entry point must be the same as its virtual address in the image
+	 * kernel (restore_jump_address), so the image kernel's
+	 * restore_registers() code doesn't find itself in a different area of
+	 * the virtual address space after switching over to the original page
+	 * tables used by the image kernel.
+	 */
+	pud = (pud_t *)get_safe_page(GFP_ATOMIC);
+	if (!pud)
+		return -ENOMEM;
+
+	pmd = (pmd_t *)get_safe_page(GFP_ATOMIC);
+	if (!pmd)
+		return -ENOMEM;
+
+	set_pmd(pmd + pmd_index(restore_jump_address),
+		__pmd((jump_address_phys & PMD_MASK) | __PAGE_KERNEL_LARGE_EXEC));
+	set_pud(pud + pud_index(restore_jump_address),
+		__pud(__pa(pmd) | _KERNPG_TABLE));
+	set_pgd(temp_level4_pgt + pgd_index(restore_jump_address),
+		__pgd(__pa(pud) | _KERNPG_TABLE));
+
+	return 0;
+}
 
 static void *alloc_pgt_page(void *context)
 {
@@ -59,9 +97,10 @@ static int set_up_temporary_mappings(void)
 	if (!temp_level4_pgt)
 		return -ENOMEM;
 
-	/* It is safe to reuse the original kernel mapping */
-	set_pgd(temp_level4_pgt + pgd_index(__START_KERNEL_map),
-		init_level4_pgt[pgd_index(__START_KERNEL_map)]);
+	/* Prepare a temporary mapping for the kernel text */
+	result = set_up_temporary_text_mapping();
+	if (result)
+		return result;
 
 	/* Set up the direct mapping from scratch */
 	for (i = 0; i < nr_pfn_mapped; i++) {
@@ -78,19 +117,50 @@ static int set_up_temporary_mappings(void)
 	return 0;
 }
 
+static int relocate_restore_code(void)
+{
+	pgd_t *pgd;
+	pud_t *pud;
+
+	relocated_restore_code = get_safe_page(GFP_ATOMIC);
+	if (!relocated_restore_code)
+		return -ENOMEM;
+
+	memcpy((void *)relocated_restore_code, &core_restore_code, PAGE_SIZE);
+
+	/* Make the page containing the relocated code executable */
+	pgd = (pgd_t *)__va(read_cr3()) + pgd_index(relocated_restore_code);
+	pud = pud_offset(pgd, relocated_restore_code);
+	if (pud_large(*pud)) {
+		set_pud(pud, __pud(pud_val(*pud) & ~_PAGE_NX));
+	} else {
+		pmd_t *pmd = pmd_offset(pud, relocated_restore_code);
+
+		if (pmd_large(*pmd)) {
+			set_pmd(pmd, __pmd(pmd_val(*pmd) & ~_PAGE_NX));
+		} else {
+			pte_t *pte = pte_offset_kernel(pmd, relocated_restore_code);
+
+			set_pte(pte, __pte(pte_val(*pte) & ~_PAGE_NX));
+		}
+	}
+	__flush_tlb_all();
+
+	return 0;
+}
+
 int swsusp_arch_resume(void)
 {
 	int error;
 
 	/* We have got enough memory and from now on we cannot recover */
-	if ((error = set_up_temporary_mappings()))
+	error = set_up_temporary_mappings();
+	if (error)
 		return error;
 
-	relocated_restore_code = (void *)get_safe_page(GFP_ATOMIC);
-	if (!relocated_restore_code)
-		return -ENOMEM;
-	memcpy(relocated_restore_code, &core_restore_code,
-	       &restore_registers - &core_restore_code);
+	error = relocate_restore_code();
+	if (error)
+		return error;
 
 	restore_image();
 	return 0;
@@ -109,11 +179,12 @@ int pfn_is_nosave(unsigned long pfn)
 
 struct restore_data_record {
 	unsigned long jump_address;
+	unsigned long jump_address_phys;
 	unsigned long cr3;
 	unsigned long magic;
 };
 
-#define RESTORE_MAGIC	0x0123456789ABCDEFUL
+#define RESTORE_MAGIC	0x123456789ABCDEF0UL
 
 /**
  *	arch_hibernation_header_save - populate the architecture specific part
@@ -126,7 +197,8 @@ int arch_hibernation_header_save(void *addr, unsigned int max_size)
 
 	if (max_size < sizeof(struct restore_data_record))
 		return -EOVERFLOW;
-	rdr->jump_address = restore_jump_address;
+	rdr->jump_address = (unsigned long)&restore_registers;
+	rdr->jump_address_phys = __pa_symbol(&restore_registers);
 	rdr->cr3 = restore_cr3;
 	rdr->magic = RESTORE_MAGIC;
 	return 0;
@@ -142,6 +214,7 @@ int arch_hibernation_header_restore(void *addr)
 	struct restore_data_record *rdr = addr;
 
 	restore_jump_address = rdr->jump_address;
+	jump_address_phys = rdr->jump_address_phys;
 	restore_cr3 = rdr->cr3;
 	return (rdr->magic == RESTORE_MAGIC) ? 0 : -EINVAL;
 }